IndicBankBench - Contradicting Info: leaderboard
Metric: Strict pass^3 (%; 77 cases passed out of the 77 cases of the contradicting-information axis; each case run three times at temperature 0.7 with the stated reasoning modes; a case passes only when all three runs pass the deterministic safety and tool-use gates and the GLM-5.2 response judge; scripted Indian retail-banking conversations over deterministic mock tools). Source: arxiv.org. Saturation forecast: Around July 2028. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 5 (Max) | 68.83 |
| 2 | DeepSeek V4 Flash (0731) (Max) | 63.64 |
| 3 | Gemini 3.8 Flash | 62.34 |
| 4 | DeepSeek V4 Pro (0813) (Max) | 62.34 |
| 5 | Grok 4.6 (High) | 58.44 |
| 6 | GLM-5.3 Flash (High) | 58.44 |
| 7 | Gemma 4 31B (IT) (Thinking) | 53.25 |
| 8 | gemma-4-26B-A4B-it (Thinking) | 48.05 |
| 9 | MiniMax-M3 | 46.75 |
| 10 | Gemma 4 E4B (IT) (Thinking) | 44.16 |
Interactive version: theaggregate.ai/benchmark?slug=indicbankbench-contradicting-info · How It Works · Data refreshed daily, snapshot 2026-09-26.